© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115876
    Prev
    Next
    INDEX
    Explanations

    equality and inequality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wedi
    -0.79
     ploughing
    -0.77
    是谁
    -0.77
     اللجنة
    -0.75
     påvir
    -0.75
    НОЙ
    -0.74
     þat
    -0.73
    經
    -0.73
     BRAD
    -0.73
    woor
    -0.72
    POSITIVE LOGITS
     equality
    2.84
     Equality
    2.20
    Equality
    2.02
    equality
    1.99
     igualdad
    1.71
     achieved
    1.40
     равен
    1.35
     attained
    1.31
     дости
    1.28
     égal
    1.20
    Activations Density 0.035%

    No Known Activations